© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 30663
    Prev
    Next
    INDEX
    Explanations

    receiving or received data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     чыга
    0.41
     usado
    0.38
    듭
    0.38
    IPAL
    0.37
     exportation
    0.37
     يستخدم
    0.37
     utilizzato
    0.36
     পাল
    0.36
     نکال
    0.35
    输
    0.35
    POSITIVE LOGITS
     received
    2.98
     receive
    2.80
     receiving
    2.59
    received
    2.59
    receive
    2.59
     Received
    2.59
    收到
    2.59
     receives
    2.58
     Receive
    2.56
     receb
    2.55
    Activations Density 0.003%

    No Known Activations